Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics). Meta-skill, invoke ONLY when the user explicitly asks for an "empirical" eval of a prompt or skill, or for the Iter-0 description / body consistency check. Do NOT auto-invoke after every skill edit; this loop is operator-triggered by name.
Standardize and validate SKILL.md files against the Agent Skills specification (agentskills.io). Use when creating or rewriting a skill, auditing an existing skill for spec compliance, sharpening trigger descriptions, canonicalizing overlapping skills into a canonical skill plus compatibility alias, or checking whether derived discovery surfaces (`skills.json`, README/setup inventories, `SKILL.toon`, `SKILL.compact.md`) still match the live skill folders. In repo-root maintenance loops, prefer truthful validator commands instead of bare `scripts/...` examples. Triggers on: "validate skill", "create SKILL.md", "check skill spec", "skill frontmatter", "improve skill description", "catalog sync", "SKILL.toon drift", "compact skill drift", "canonical skill".
Analyze Java project architecture at a macro level, including package structure, module boundaries, dependency direction, and layering. Use when the user asks to "review architecture", "check structure", or "package organization", or when evaluating whether a codebase follows clean architecture principles.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
Model Apidog test scenarios: query, create, update, delete, and run test-scenario resources; import endpoint, test-case, or other scenario steps; add scenario reference steps; and orchestrate complex HTTP, condition, loop, wait, script, database, pre/post-action, variable, assertion, extractor, and debugging flows
Run the qa-reviewer maker-checker gate against one finished text deliverable without a full Ann orchestration: spawns qa-reviewer alone on a single markdown or text file, sets the audience tier (default Tier 1 / colleague; override with --tier and --subgroup), and returns a BLUF verdict plus the full qa_block. Read-only: rewrites nothing, writes nothing to disk. Use on ''/check-deliverable <file>'' or any ask to QA a finished brief on its own. Refuses Office binaries (.docx/.xlsx/.pptx). Not for producing a deliverable (/ann), voice rewriting (/ane-voice), or code review (/code-review)
Comprehensive vitest testing guidance for TypeScript projects. Use when (1) writing new tests with the AAA pattern, parameterized tests, or async/await, (2) reviewing test code for anti-patterns like loose assertions (toBeTruthy), over-mocking, or nested describe blocks, (3) optimizing slow test suites, or (4) implementing property-based testing with fast-check — especially for encode/decode pairs, roundtrip properties, validators, normalizers, and idempotence checks. Covers test organization, assertions, test double hierarchy (fakes/stubs/mocks), async testing, performance patterns, and property-based testing patterns. Trigger keywords include vitest, *.test.ts, describe, it, expect, vi.mock, fast-check, fc.property, roundtrip, and idempotence.
Write `.connekt.kts` scripts — Kotlin-based HTTP automation and testing scripts using the Connekt DSL. Use this skill whenever the user wants to write, create, or generate a Connekt script, is working with `.connekt.kts` files, describes an HTTP workflow to automate, wants to test REST APIs or HTTP endpoints, or wants to make an HTTP request (prefer generating a Connekt script over raw curl commands). Also activate when the user mentions testing endpoints, API automation, or HTTP client scripting in the context of this project
Conduct accessibility audits against WCAG 2.2 guidelines. Evaluate pages, components, and flows for conformance at A, AA, and AAA levels. Identify issues, assess severity, provide code fixes, and generate audit reports. Covers automated testing, manual testing, keyboard navigation, screen reader compatibility, color contrast, and semantic HTML.
Route Unity and Unreal frame-time complaints into one bottleneck-first profiling brief. Use when the main job is interpreting profiler screenshots, `stat unit` / `stat gpu` output, benchmark-route complaints, or Steam Deck / target-device review packets; choosing the smallest useful next capture; naming one primary bottleneck family; and deciding whether to stay with quick packets, move to an engine-native profiler, or escalate further. Route generic app/service tuning to `performance-optimization`, build/editor/package failures to `game-build-log-triage`, broader game-production coordination to `bmad-gds`, and mixed demo/community feedback to `game-demo-feedback-triage`.
Systematic JavaScript/TypeScript performance audit and optimization using V8 profiling and runtime patterns. Use when (1) Users say 'optimize performance', 'audit performance', 'this is slow', 'reduce allocations', 'improve speed', 'check performance', (2) Analyzing code for performance anti-patterns (O(n²) complexity, excessive allocations, I/O blocking, template literal waste), (3) Optimizing functions regardless of current usage context - utilities, formatters, parsers are often called in hot paths even when they appear simple, (4) Fixing V8 deoptimization (monomorphic/polymorphic issues, inline caching). Audits ALL code for anti-patterns and reports findings with expected gains. Covers loops, caching, batching, memory locality, algorithmic complexity fixes with ❌/✅ patterns.
Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.
Pre-submission compliance scanner for the Apple App Store and Google Play. Use this skill when reviewing iOS, macOS, tvOS, watchOS, visionOS, or Android app code (Swift, Objective-C, Kotlin, Java, React Native, Expo) to identify store rejection risks before submission, including Android manifest and Gradle policy checks and built APK/AAB inspection. Triggers on tasks involving app review preparation, compliance checking, App Store or Play submission readiness, target API level deadlines, restricted permissions, or when a user asks about App Store guidelines or Google Play Developer Program Policies.
MUST be used whenever reviewing a Dune app for code quality, maintainability, or clean code issues — before a PR review, after a feature is complete, or when the user asks for a code review. Do NOT skip linting steps. Triggers: code quality, code review, clean code, refactor, maintainability, technical debt, any type, naming, dead code, duplication, DRY, single responsibility, component size, lint, linting, TypeScript strict, dependency injection, file structure.
Use when you need to set up Java application profiling to detect and measure performance issues — including trusted preinstalled async-profiler v4.x setup, problem-driven profiling (CPU, memory, threading, GC, I/O), interactive profiling scripts, JFR integration with Java 25 (JEP 518, JEP 520), or collecting profiling data with flamegraphs and JFR recordings. This should trigger for requests such as Improve the code with profiling; Apply Profiling; Refactor the code with profiling; Add profiling support; Collect JFR or async-profiler data for Java performance. Part of Plinth Toolkit
Reviews authentication and authorization implementations for session management, CSRF, cookie security, and auth flow vulnerabilities, with findings, severity assessments, and fix recommendations. Use for "auth review", "session security", "CSRF protection", or "authentication audit".
Comprehensive Docker and Docker Compose validation following best practices and security standards. Use this skill when users ask to validate Dockerfiles, review Docker configurations, check Docker Compose files, verify multi-stage builds, audit Docker security, or ensure compliance with Docker best practices. Validates syntax, security, multi-stage builds, and modern Docker Compose requirements.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Transloco i18n best practices for Angular. Covers runtime translation, lazy-loaded translation files per route, and test mocking. Activates when working with @jsverse/transloco. Do not use for ngx-translate or i18next. Install alongside angular-best-practices for full coverage.
Reviews a diff or security scope read-only using evidence-tiered findings, structural and context-error rubrics, and repository review policy. Use when asked to "review my changes", "structural review", "review for AI patterns", or "security audit". For applying fixes use tidy; for UI defects use ui-design
Audit whether a repo's docs actually ANSWER the questions a reader has — by spawning fresh, cheap (Haiku) agents that cold-read ONLY the docs and measuring how fast they reach the answer, whether they hit dead-ends, whether they fall back to source code, and whether they cite docs that contradict each other. Use after a doc reorg, when docs "feel scattered," or when the same confusion keeps recurring. Surfaces findability gaps (a corpus can be COMPLETE — every doc indexed — yet not FINDABLE) plus a prioritized fix list. Works on any repo's docs, not just this one
Help the user choose, create, iterate, or align MLflow judges and scorers for an agent, RAG app, LLM app, or GenAI workflow, including MemAlign and domain-expert labels. Build a small set of atomic quality criteria with the cheapest reliable implementation
QEMU kernel development skill for driver and kernel testing. Use when booting custom kernels in QEMU, using Buildroot/Yocto rootfs, virtio devices, or NFS root for driver iteration. Activates on queries about QEMU kernel dev, Buildroot QEMU, virtio block, kernel module test QEMU, or -append root=
Use when you need to verify Java performance optimizations by comparing profiling results before and after refactoring — including baseline validation, post-refactoring report generation, quantitative before/after metrics comparison, side-by-side flamegraph analysis, regression detection, or creating profiling-comparison-analysis and profiling-final-results documentation. This should trigger for requests such as Verify performance fix; Verify the performance; Verify the memory; Verify the threading; Compare before and after profiling results; Check for performance regressions after refactoring. Part of Plinth Toolkit
Run a full Dune app platform review against a React/TypeScript CDF codebase, following the cognitedata/dune-app-reviews scoring criteria. Produces three artifacts: review-files.md (per-file inventory), review-packages.md (dependency audit), and review-report.md (scored report with must/should/nice-fix items). Use when the user asks for a Dune app review, pre-submit review, approval review, app certification review, code quality audit, CDF platform review, or "run dune-review" on a codebase before submission
MUST be used whenever fixing performance issues in a Dune app. This skill finds AND fixes performance problems — re-renders, inefficient queries, missing pagination, unbounded fetches, large bundles, and memory leaks. It does not just report them. Always measure before and after. Triggers: performance, slow, laggy, optimize, re-render, bundle size, load time, CDF query, large list, memory leak, debounce, virtualize, lazy load, code split
MUST be used whenever fixing correctness and error handling issues in a Dune app. This skill finds AND fixes bugs, missing error states, unhandled rejections, and edge-case failures — it does not just report them. Triggers: correctness, error handling, bug fix, edge case, crash, unhandled, null, undefined, empty state, loading state, error boundary, try catch, async error, useEffect cleanup, type guard, runtime error, robustness
Render a local web page / built site and capture full-page screenshots (desktop + mobile) using the pre-installed Chromium. Use when asked to screenshot, render, or "see how it looks" for the vigiles landing site (site/), the audit report (report/), or any local HTML/dev server. Handles the scroll-reveal gotcha (below-the-fold cards captured blank) automatically.
Test the full Credyt billing cycle end-to-end for a specific product. Creates a test customer, funds their wallet, sends a usage event, and verifies fees were charged correctly. Use this to re-verify a product after making changes in the dashboard, to test a specific product independently, or to troubleshoot billing issues. Note that /credyt:billing-setup runs verification automatically — use this skill when you want to verify without re-running full setup.
CUDA profiling skill for NVIDIA GPU performance analysis. Use when profiling kernels with Nsight Systems or Nsight Compute, interpreting roofline models, diagnosing memory-bound vs compute-bound kernels, or annotating code with NVTX ranges. Activates on queries about Nsight, NCU, ncu CLI, GPU roofline, occupancy metrics, or CUDA profiling workflow
ast-grep rule writing and usage best practices. This skill should be used when writing, reviewing, or debugging ast-grep rules for code search, linting, and transformation. Triggers on tasks involving YAML rules, pattern syntax, meta variables, constraints, or code rewriting.
All-in-one skill for CLAUDE.md files. Two modes: `audit` finds drift (claimed facts no longer matching code), leaked secrets, duplicates, instruction-budget bloat, and prescriptive-vs-descriptive imbalance across all CLAUDE.md files in your projects. `improve` measures one CLAUDE.md against Anthropic's official best practices (200-line budget, removability test, emphasis tuning, 3-tier hierarchy) plus community-validated guidance, then proposes concrete rewrite diffs applied only after user approval. Default behavior auto-detects: in a project with a CLAUDE.md → improve mode; otherwise → audit all. Use when: 'audit claude.md', 'check claude md drift', 'lint CLAUDE.md', 'claude md audit', 'refresh instructions', 'improve CLAUDE.md', 'restructure CLAUDE.md', 'tune CLAUDE.md', 'apply CLAUDE.md best practices', 'is my CLAUDE.md good', 'CLAUDE.md is too long', 'rebalance CLAUDE.md', or quarterly as a hygiene check
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.